INDEX

Explanations

information related to trees

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ysis

-0.69

 Doyle

-0.67

 Hebdo

-0.66

 Commodore

-0.64

xes

-0.63

 Mellon

-0.62

oice

-0.62

DOS

-0.60

abwe

-0.60

 Pric

-0.59

POSITIVE LOGITS

 vegetation

1.09

grass

1.07

 grass

0.99

lands

0.95

wood

0.92

 foliage

0.92

 gardens

0.91

vale

0.91

 forests

0.87

ieri

0.87

Activations Density 2.428%

information related to trees

No Comments

No Known Activations

information related to trees

No Comments

No Known Activations